Skip to content
Discussion options

You must be logged in to vote

It's not really tractable cause every used has different gpu with different memory. Providing A100 as a baseline is possible but there are too many variations of model configs to manually test the peak memory and batch size.

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by mehadi92
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants